Development of a Novel Scoring System to Quantify the Severity of Incident Reports: An Exploratory Research Study

Uematsu, Haruhiro; Uemura, Masakazu; Kurihara, Masaru; Umemura, Tomomi; Hiramatsu, Masayuki; Kitano, Fumimasa; Fukami, T.; Nagao, Yoshimasa

doi:10.1007/s10916-022-01893-1

Cited by 3 publications

(12 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More importantly, higher error scores for departments were associated with a higher submission rate of error-containing incident reports. This phenomenon was also observed for group severity scores which indicate the severity of incidents using this model 14. Severe events rarely occur, but events associated with errors are relatively common.…”

Section: Discussionsupporting

confidence: 56%

“…Severity is classified into five categories using the grading system developed at NUH: ‘Near Miss’, ‘No Harm’, ‘Low Harm’, ‘Severe Harm’ and ‘Catastrophic/Fatal Event’. It has similarities with other grading systems such as those of the WHO and National University Hospital Council of Japan 14…”

Section: Methodsmentioning

confidence: 89%

“…Various vectorisation methods, such as binary, term frequency, thresholding and term frequency-inverse document frequency methods, are generally used to transform segmented terms into numerical representations 29. We adopted the same vectorisation method to weigh semantic characteristics as was applied to the severity score, which is used to quantify event severity on the basis of training data and GRM classifications 14. The severity score can also be used to predict organisational trends.…”

Section: Discussionmentioning

confidence: 99%

“…A study on severity scores highlighted that many terms used in reports of severe incidents did not appear in reports of non-severe incidents. However, that study had a huge number of non-severe incident reports and far fewer severe reports 14. To alleviate this imbalance, the formula was updated in this study by adding one.…”

Section: Discussionmentioning

confidence: 99%

“…Studies have explored how to obtain better value from incident reports using health information technologies. One recent study proposed an original decision-making model that partly relies on natural language processing (NLP) techniques to quantify the severity of incidents from aggregated big data and measure organisational trends using the central limit theorem 14. This model was novel in two ways.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Development of a scoring system to quantify errors from semantic characteristics in incident reports

Uematsu,

Uemura,

Kurihara

et al. 2024

BMJ Health Care Inform

Self Cite

View full text Add to dashboard Cite

ObjectivesIncident reporting systems are widely used to identify risks and enable organisational learning. Free-text descriptions contain important information about factors associated with incidents. This study aimed to develop error scores by extracting information about the presence of error factors in incidents using an original decision-making model that partly relies on natural language processing techniques.MethodsWe retrospectively analysed free-text data from reports of incidents between January 2012 and December 2022 from Nagoya University Hospital, Japan. The sample data were randomly allocated to equal-sized training and validation datasets. We conducted morphological analysis on free text to segment terms from sentences in the training dataset. We calculated error scores for terms, individual reports and reports from staff groups according to report volume size and compared these with conventional classifications by patient safety experts. We also calculated accuracy, recall, precision and F-score values from the proposed ‘report error score’.ResultsOverall, 114 013 reports were included. We calculated 36 131 ‘term error scores’ from the 57 006 reports in the training dataset. There was a significant difference in error scores between reports of incidents categorised by experts as arising from errors (p<0.001,d=0.73 (large)) and other incidents. The accuracy, recall, precision and F-score values were 0.8, 0.82, 0.85 and 0.84, respectively. Group error scores were positively associated with expert ratings (correlation coefficient, 0.66; 95% CI 0.54 to 0.75, p<0.001) for all departments.ConclusionOur error scoring system could provide insights to improve patient safety using aggregated incident report data.

show abstract

Section: Discussionsupporting

confidence: 56%

Section: Methodsmentioning

confidence: 89%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Development of a scoring system to quantify errors from semantic characteristics in incident reports

Uematsu,

Uemura,

Kurihara

et al. 2024

BMJ Health Care Inform

Self Cite

View full text Add to dashboard Cite

show abstract

Patient engagement with psychological safety

Fukami

2023

Dialogues in Health

Self Cite

View full text Add to dashboard Cite

Enhancing Healthcare Accountability for Administrators: Fostering Transparency for Patient Safety and Quality Enhancement

Fukami

2024

Cureus

View full text Add to dashboard Cite

Transparency in healthcare organizations is essential for creating a culture of patient-centered care where patients are respected, informed, and actively engaged in their health and well-being. Organizational transparency is a crucial element in healthcare, enhancing patient safety and quality improvement. Transparency involves open communication about healthcare organizations' performance, outcomes, and processes, leading to improved accountability, trust, and patient engagement. Transparent organizations prioritize patient-centered care, involving patients in decision-making and fostering shared mental models between healthcare providers and patients. Psychological safety is vital for organizational transparency. Patient safety reporting systems play a key role in transparency, allowing anonymous reporting of safety concerns and incidents. These systems facilitate early risk identification, continuous improvement, and compliance with regulatory requirements. Transparency in reporting encourages a culture of openness, learning from near misses, and addressing systemic issues and human errors. It aligns with ethical principles, potentially mitigating legal challenges. This review synthesizes key themes, including the importance of patient-centered care, the role of psychological safety in fostering transparency, and the effectiveness of patient safety reporting systems.

show abstract

Development of a Novel Scoring System to Quantify the Severity of Incident Reports: An Exploratory Research Study

Cited by 3 publications

References 29 publications

Development of a scoring system to quantify errors from semantic characteristics in incident reports

Development of a scoring system to quantify errors from semantic characteristics in incident reports

Patient engagement with psychological safety

Enhancing Healthcare Accountability for Administrators: Fostering Transparency for Patient Safety and Quality Enhancement

Contact Info

Product

Resources

About